MediumVulnerabilityLLM-specific
CVE-2025-48887: vLLM regular expression denial of service in pythonic tool parser
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2025-48887
- Published
- Record updated
- Affected
- vllm >= 0.6.4, < 0.9.0
- Fixed in
- 0.9.0
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.5%
Summary
vLLM, an inference and serving engine for large language models (LLMs), contains a Regular Expression Denial of Service (ReDoS) flaw in `vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py` in versions 0.6.4 up to but excluding 0.9.0. The tool call detection regex uses multiple nested quantifiers, optional groups and inner repetitions, so an attacker can trigger catastrophic backtracking, severely degrading performance or making the service unavailable.
Mitigation
Version 0.9.0 contains a patch for the issue.
Topics
Related items
- HighHermes Agent - Pre-Authentication Disk ConsumptionSimilar attack · Tenable Research Advisories
- MediumHermes Agent - Pre-Authentication Memory ExhaustionSimilar attack · Tenable Research Advisories
- MediumGHSA-v36g-jcw9-x7cw: Pydantic AI: Excessive resource use when local web fetching converts nested HTMLSimilar attack · GitHub Advisory Database
- MediumGHSA-v2xh-2vp8-57h8: Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrlSimilar attack · GitHub Advisory Database
- MediumGHSA-fpf4-vwcp-v4hp: Pydantic AI: Event loop blocked by quadratic title extraction in `web_fetch`Similar attack · GitHub Advisory Database